English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The recent series of innovations in deep learning (DL) have shown enormouspotential to impact individuals and society, both positively and negatively.The DL models utilizing massive computing power and enormous datasets havesignificantly outperformed prior historical benchmarks on increasinglydifficult, well-defined research tasks across technology domains such ascomputer vision, natural language processing, signal processing, andhuman-computer interactions. However, the Black-Box nature of DL models andtheir over-reliance on massive amounts of data condensed into labels and denserepresentations poses challenges for interpretability and explainability of thesystem. Furthermore, DLs have not yet been proven in their ability toeffectively utilize relevant domain knowledge and experience critical to humanunderstanding. This aspect is missing in early data-focused approaches andnecessitated knowledge-infused learning and other strategies to incorporatecomputational knowledge. This article demonstrates how knowledge, provided as aknowledge graph, is incorporated into DL methods using knowledge-infusedlearning, which is one of the strategies. We then discuss how this makes afundamental difference in the interpretability and explainability of currentapproaches, and illustrate it with examples from natural language processingfor healthcare and education applications.

Semantics of the Black-Box: Can knowledge graphs help make deep learning systems more interpretable and explainable?